{"id":"https://openalex.org/W2908815110","doi":"https://doi.org/10.1109/iros.2018.8593619","title":"Deep Q-Learning for Dry Stacking Irregular Objects","display_name":"Deep Q-Learning for Dry Stacking Irregular Objects","publication_year":2018,"publication_date":"2018-10-01","ids":{"openalex":"https://openalex.org/W2908815110","doi":"https://doi.org/10.1109/iros.2018.8593619","mag":"2908815110"},"language":"en","primary_location":{"id":"doi:10.1109/iros.2018.8593619","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2018.8593619","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yifang Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yifang Liu","raw_affiliation_strings":["Department of Computer Science and Engineering, University at Buffalo, Buffalo, NY, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University at Buffalo, Buffalo, NY, USA","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062638638","display_name":"Seyed Mahdi Shamsi","orcid":null},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Seyed Mahdi Shamsi","raw_affiliation_strings":["Department of Computer Science and Engineering, University at Buffalo, Buffalo, NY, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University at Buffalo, Buffalo, NY, USA","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102710848","display_name":"Le Fang","orcid":"https://orcid.org/0000-0002-8923-537X"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Le Fang","raw_affiliation_strings":["Department of Computer Science and Engineering, University at Buffalo, Buffalo, NY, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University at Buffalo, Buffalo, NY, USA","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102745649","display_name":"Changyou Chen","orcid":"https://orcid.org/0000-0002-3230-2770"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Changyou Chen","raw_affiliation_strings":["Department of Computer Science and Engineering, University at Buffalo, Buffalo, NY, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University at Buffalo, Buffalo, NY, USA","institution_ids":["https://openalex.org/I63190737"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056528269","display_name":"Nils Napp","orcid":"https://orcid.org/0000-0002-1694-0393"},"institutions":[{"id":"https://openalex.org/I63190737","display_name":"University at Buffalo, State University of New York","ror":"https://ror.org/01y64my43","country_code":"US","type":"education","lineage":["https://openalex.org/I63190737"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nils Napp","raw_affiliation_strings":["Department of Computer Science and Engineering, University at Buffalo, Buffalo, NY, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University at Buffalo, Buffalo, NY, USA","institution_ids":["https://openalex.org/I63190737"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I63190737"],"apc_list":null,"apc_paid":null,"fwci":1.1657,"has_fulltext":false,"cited_by_count":16,"citation_normalized_percentile":{"value":0.80355088,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1569","last_page":"1576"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12190","display_name":"Innovations in Concrete and Construction Materials","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12190","display_name":"Innovations in Concrete and Construction Materials","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10653","display_name":"Robot Manipulation and Learning","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9865999817848206,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8110982179641724},{"id":"https://openalex.org/keywords/heuristics","display_name":"Heuristics","score":0.7364997863769531},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6557813286781311},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6300131678581238},{"id":"https://openalex.org/keywords/stacking","display_name":"Stacking","score":0.6169653534889221},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.5611603260040283},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5346813201904297},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5141677856445312},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.4890792965888977},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.47437459230422974},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.45903444290161133},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.44330549240112305},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.43417754769325256},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3805680572986603},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.2791212201118469}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8110982179641724},{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.7364997863769531},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6557813286781311},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6300131678581238},{"id":"https://openalex.org/C33347731","wikidata":"https://www.wikidata.org/wiki/Q285210","display_name":"Stacking","level":2,"score":0.6169653534889221},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.5611603260040283},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5346813201904297},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5141677856445312},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.4890792965888977},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.47437459230422974},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.45903444290161133},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.44330549240112305},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.43417754769325256},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3805680572986603},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2791212201118469},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C46141821","wikidata":"https://www.wikidata.org/wiki/Q209402","display_name":"Nuclear magnetic resonance","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros.2018.8593619","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros.2018.8593619","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.7300000190734863,"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1840337046","https://openalex.org/W1978623453","https://openalex.org/W1979101522","https://openalex.org/W2018273065","https://openalex.org/W2030775133","https://openalex.org/W2043164756","https://openalex.org/W2110762409","https://openalex.org/W2115536039","https://openalex.org/W2126909264","https://openalex.org/W2145339207","https://openalex.org/W2194775991","https://openalex.org/W2245805501","https://openalex.org/W2257979135","https://openalex.org/W2280321973","https://openalex.org/W2554984891","https://openalex.org/W2600581678","https://openalex.org/W2762487195","https://openalex.org/W2890445280","https://openalex.org/W2950492145","https://openalex.org/W2962957005","https://openalex.org/W2963014947","https://openalex.org/W2963864421","https://openalex.org/W4255385909","https://openalex.org/W6684921986","https://openalex.org/W6713055699","https://openalex.org/W6729507393"],"related_works":["https://openalex.org/W2035329725","https://openalex.org/W4376641153","https://openalex.org/W2050788868","https://openalex.org/W2070875936","https://openalex.org/W4250391473","https://openalex.org/W3045075405","https://openalex.org/W4302292679","https://openalex.org/W2956222435","https://openalex.org/W4241625287","https://openalex.org/W4295885776"],"abstract_inverted_index":{"We":[0,66,146],"propose":[1],"a":[2,22,33,59,68,91,107,141,156],"reinforcement":[3,69],"learning":[4,70],"approach":[5],"for":[6,38],"automatically":[7],"building":[8],"dry":[9],"stacked":[10],"(i.e.":[11],"no":[12],"mortar)":[13],"structures":[14],"with":[15,138],"irregular":[16,19,161],"objects.":[17,162],"Stacking":[18],"objects":[20,139],"is":[21,88,99,103],"challenging":[23],"problem":[24],"since":[25],"each":[26],"assembly":[27],"action":[28,97],"can":[29],"be":[30],"drawn":[31],"from":[32],"continuous":[34,100],"space":[35,98],"of":[36,63,110,144],"poses":[37],"an":[39],"object,":[40],"and":[41,45,116,159],"several":[42],"local":[43],"geometric":[44,115],"physical":[46,117],"considerations":[47],"strongly":[48],"affect":[49],"the":[50,64,77,96,101,121,127,148],"stability.":[51],"To":[52],"tackle":[53],"this":[54],"challenge,":[55],"we":[56],"concentrate":[57],"on":[58,73],"simplified":[60],"2D":[61],"version":[62],"problem.":[65],"present":[67],"algorithm":[71],"based":[72],"deep":[74,92],"Q-learning,":[75],"where":[76],"learned":[78],"Q-function,":[79],"which":[80],"maps":[81],"state-action":[82],"pairs":[83],"into":[84],"expected":[85],"long-term":[86],"rewards,":[87],"represented":[89],"by":[90,105,152],"neural":[93],"network.":[94],"As":[95],"Q-network":[102],"trained":[104],"sampling":[106],"finite":[108],"number":[109],"actions":[111],"that":[112,126],"consider":[113],"both":[114],"constraints":[118],"to":[119,135],"approximate":[120],"target":[122],"Q-values,":[123],"Experiments":[124],"show":[125],"proposed":[128],"method":[129],"outperforms":[130],"previous":[131],"heuristics-based":[132],"planning,":[133],"leading":[134],"super":[136],"construction":[137],"containing":[140],"significant":[142],"amount":[143],"variations.":[145],"validate":[147],"generated":[149],"stacking":[150],"plans":[151],"executing":[153],"them":[154],"using":[155],"robot":[157],"arm":[158],"manufactured,":[160]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}